whisper.cpp
whisper.cpp copied to clipboard
Issue compiling master on clang / gcc
Seems to be the same issue at: https://github.com/ggerganov/llama.cpp/issues/4208
I CC: clang version 17.0.6 (Red Hat 17.0.6-1.0.1.module+el8.10.0+90260+0be6147c) I CXX: gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-22.0.1) I NVCC: Build cuda_12.2.r12.2/compiler.33191640_0
!!! DEPRECATION WARNING !!! The following WHISPER_ options are deprecated and will be removed in the future. Use the GGML_ prefix instead
- WHISPER_CUDA
- WHISPER_METAL
- WHISPER_OPENMP
- WHISPER_RPC
- WHISPER_SYCL
- WHISPER_SYCL_F16
- WHISPER_OPENBLAS
- WHISPER_OPENBLAS64
- WHISPER_BLIS
- WHISPER_NO_LLAMAFILE
- WHISPER_NO_ACCELERATE
- WHISPER_NO_OPENMP
- WHISPER_NO_METAL
nvcc -std=c++11 -O3 -use_fast_math --forward-unknown-to-host-compiler -arch=native -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_MMV_Y=1 -DK_QUANTS_PER_ITERATION=2 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -Iggml/include -Iggml/src -Iinclude -Isrc -Iexamples -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_OPENMP -DGGML_USE_CUDA -I/usr/local/cuda/include -I/usr/local/cuda/targets/x86_64-linux/include -Xcompiler "-std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -fopenmp -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi -Wno-pedantic" -c ggml/src/ggml-cuda.cu -o ggml/src/ggml-cuda.o nvcc warning : Cannot find valid GPU for '-arch=native', default arch is used gcc: error: unrecognized command line option
Seems to have been introduced in June? 1.6.2 compiles without issue.